Machine learning models as an alternative to determine productivity losses caused by weeds

Weed control can be economically viable if implemented at the necessary time to minimize interference. Empirical mathematical models have been used to determine when to start the weed control in many crops. Furthermore, empirical models have a low generalization capacity to understand different scenarios. However, computational development facilitated the implementation of supervised machine learning models, as artificial neural networks (ANNs), capable of understanding complex relationships. The objectives of our work were to evaluate the ability of ANNs to estimate yield losses in onion (model crop) due to weed interference and compare with multiple linear regression (MLR) and empirical models.

MLR constructed from non-destructive and destructive methods show R² and root mean square error (RMSE) values varying between 0.75% and 0.82%, 13.0% and 19.0%, respectively, during testing step. The ANNs has higher R² (higher than 0.95) and lower RMSE (less than 6.95%) compared to MLR and empirical models for training and testing steps. ANNs considering only the coexistence period and system have similar performance to MLR models. However, the insertion of variables related to weed density (non-destructive ANN) or fresh matter (destructive ANN) increases the predictive capacity of the networks to values close to 99% correct.

The best performing ANNs can indicate the beginning of weed control since they can accurately estimate losses due to competition. These results encourage future studies implementing ANNs based on computer vision to extract information about the weed community.